DQN算法打印迭代奖励值代码

好的，以下是使用DQN算法打印迭代奖励值的代码示例：

import gym
import numpy as np
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.optimizers import Adam

class DQNAgent:
    def __init__(self, state_size, action_size):
        self.state_size = state_size
        self.action_size = action_size
        self.memory = []
        self.gamma = 0.95
        self.epsilon = 1.0
        self.epsilon_decay = 0.995
        self.epsilon_min = 0.01
        self.learning_rate = 0.001
        self.model = self._build_model()

    def _build_model(self):
        model = Sequential()
        model.add(Dense(24, input_dim=self.state_size, activation='relu'))
        model.add(Dense(24, activation='relu'))
        model.add(Dense(self.action_size, activation='linear'))
        model.compile(loss='mse', optimizer=Adam(lr=self.learning_rate))
        return model

    def remember(self, state, action, reward, next_state, done):
        self.memory.append((state, action, reward, next_state, done))

    def act(self, state):
        if np.random.rand() <= self.epsilon:
            return np.random.choice(self.action_size)
        else:
            return np.argmax(self.model.predict(state)[0])

    def replay(self, batch_size):
        minibatch = np.random.choice(len(self.memory), batch_size, replace=False)
        for state, action, reward, next_state, done in minibatch:
            target = reward
            if not done:
                target = reward + self.gamma * np.amax(self.model.predict(next_state)[0])
            target_f = self.model.predict(state)
            target_f[0][action] = target
            self.model.fit(state, target_f, epochs=1, verbose=0)
        if self.epsilon > self.epsilon_min:
            self.epsilon *= self.epsilon_decay

def train(agent, env, episodes, batch_size):
    rewards = []
    for episode in range(episodes):
        state = env.reset()
        state = np.reshape(state, [1, agent.state_size])
        done = False
        total_reward = 0
        while not done:
            action = agent.act(state)
            next_state, reward, done, _ = env.step(action)
            next_state = np.reshape(next_state, [1, agent.state_size])
            agent.remember(state, action, reward, next_state, done)
            state = next_state
            total_reward += reward
        if len(agent.memory) > batch_size:
            agent.replay(batch_size)
        rewards.append(total_reward)
        print("Episode: {}/{}, Reward: {}".format(episode+1, episodes, total_reward))
    return rewards

if __name__ == "__main__":
    env = gym.make('CartPole-v0')
    state_size = env.observation_space.shape[0]
    action_size = env.action_space.n
    agent = DQNAgent(state_size, action_size)
    episodes = 100
    batch_size = 32
    rewards = train(agent, env, episodes, batch_size)
    print("Average reward over {} episodes: {}".format(episodes, sum(rewards)/episodes))

在训练过程中，每个 episode 结束后会打印出这个 episode 的迭代奖励值。最后会输出平均奖励值。